⚡
Performance benchmark
How fast is the model?
Raw throughput on real hardware – how many tokens a model generates per second, how quickly it processes the prompt and how short the time to first token is. Higher is better.
⚡ Generation (tok/s)🔄 Prefill⏱️ TTFT👥 Concurrency
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 826,24 tok/s TG Prefill 3.229 · TTFT 15.223 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 2 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 474,76 tok/s TG Prefill 1.760 · TTFT 26.540 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 3 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 436,25 tok/s TG Prefill 3.526 · TTFT 5.370 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 4 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 351,55 tok/s TG Prefill 1.164 · TTFT 38.427 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 5 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 333,12 tok/s TG Prefill 1.168 · TTFT 37.996 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 6 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 267,65 tok/s TG Prefill 1.544 · TTFT 9.962 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 7 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,63 tok/s TG Prefill 993 · TTFT 14.781 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 8 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,55 tok/s TG Prefill 1.000 · TTFT 14.742 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 9 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 143,56 tok/s TG Prefill 1.267 · TTFT 4.040 ms | 10× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLQ4_K_M | Details → | |
| 10 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 140,06 tok/s TG Prefill 1.284 · TTFT 1.994 ms | 5× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLQ4_K_M | Details → | |
| 11 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,26 tok/s TG Prefill 1.113 · TTFT 2.031 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 12 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,52 tok/s TG Prefill 1.096 · TTFT 2.336 ms | 5× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLUD-Q4_K_M | Details → | |
| 13 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 105,04 tok/s TG Prefill 1.089 · TTFT 4.703 ms | 10× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLUD-Q4_K_M | Details → | |
| 14 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,70 tok/s TG Prefill 1.022 · TTFT 2.264 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 15 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,07 tok/s TG Prefill 383 · TTFT 4.502 ms | 5× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 16 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,10 tok/s TG Prefill 816 · TTFT 627 ms | 1× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLQ4_K_M | Details → | |
| 17 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,84 tok/s TG Prefill 920 · TTFT 2.098 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 18 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 66,43 tok/s TG Prefill 898 · TTFT 2.781 ms | 1× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 19 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,18 tok/s TG Prefill 592 · TTFT 865 ms | 1× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLUD-Q4_K_M | Details → | |
| 20 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,23 tok/s TG Prefill 357 · TTFT 14.331 ms | 10× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLQ8_0 | Details → | |
| 21 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,58 tok/s TG Prefill 348 · TTFT 7.358 ms | 5× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLQ8_0 | Details → | |
| 22 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 42,11 tok/s TG Prefill 821 · TTFT 2.298 ms | 1× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | openclaw_cli | Details → | |
| 23 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,94 tok/s TG Prefill 70 · TTFT 161.804 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 24 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,41 tok/s TG Prefill 50 · TTFT 226.449 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 25 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,57 tok/s TG Prefill 50 · TTFT 276.964 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 26 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,68 tok/s TG Prefill 182 · TTFT 2.809 ms | 1× | Intel Arc Pro B70 iAMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCLQ8_0 | Details → | |
| 27 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,64 tok/s TG Prefill 281 · TTFT 6.718 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 28 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,18 tok/s TG Prefill 319 · TTFT 8.542 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 29 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 17,72 tok/s TG Prefill 45 · TTFT 32.857 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 30 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,82 tok/s TG Prefill 40 · TTFT 49.516 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 31 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,00 tok/s TG Prefill 15 · TTFT 531 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 32 | command-a-reasoning-08-2025111BCohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,02 tok/s TG Prefill 5 · TTFT 485.856 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |